| { | |
| "best_metric": 1.9968057870864868, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.746268656716418, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014925373134328358, | |
| "grad_norm": 0.30074843764305115, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7593, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014925373134328358, | |
| "eval_loss": 2.4016451835632324, | |
| "eval_runtime": 0.979, | |
| "eval_samples_per_second": 115.424, | |
| "eval_steps_per_second": 15.322, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029850746268656716, | |
| "grad_norm": 0.3124169409275055, | |
| "learning_rate": 4e-05, | |
| "loss": 1.8847, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04477611940298507, | |
| "grad_norm": 0.3307819962501526, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1815, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05970149253731343, | |
| "grad_norm": 0.39875397086143494, | |
| "learning_rate": 8e-05, | |
| "loss": 2.2626, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07462686567164178, | |
| "grad_norm": 0.3945293426513672, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1814, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08955223880597014, | |
| "grad_norm": 0.3672662377357483, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 2.2924, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1044776119402985, | |
| "grad_norm": 0.37927067279815674, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.4045, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11940298507462686, | |
| "grad_norm": 0.402125746011734, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.1665, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.13432835820895522, | |
| "grad_norm": 0.49144914746284485, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.287, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.14925373134328357, | |
| "grad_norm": 0.4933624565601349, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.3176, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16417910447761194, | |
| "grad_norm": 0.4840998351573944, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.3052, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1791044776119403, | |
| "grad_norm": 0.48531755805015564, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.3138, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.19402985074626866, | |
| "grad_norm": 0.5164350271224976, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 2.0854, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.208955223880597, | |
| "grad_norm": 0.5610319972038269, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.3273, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.22388059701492538, | |
| "grad_norm": 0.6317114233970642, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.3732, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.23880597014925373, | |
| "grad_norm": 0.8776953816413879, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 2.2796, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2537313432835821, | |
| "grad_norm": 0.33381423354148865, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.7108, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.26865671641791045, | |
| "grad_norm": 0.2970743477344513, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 1.5712, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2835820895522388, | |
| "grad_norm": 0.37099114060401917, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 1.937, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.29850746268656714, | |
| "grad_norm": 0.3620712459087372, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.0657, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.31343283582089554, | |
| "grad_norm": 0.34259912371635437, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 1.9633, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3283582089552239, | |
| "grad_norm": 0.4164319932460785, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 2.2391, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.34328358208955223, | |
| "grad_norm": 0.34018903970718384, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.1109, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3582089552238806, | |
| "grad_norm": 0.36194512248039246, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 2.1308, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.373134328358209, | |
| "grad_norm": 0.36260104179382324, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 2.0707, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.373134328358209, | |
| "eval_loss": 2.055764675140381, | |
| "eval_runtime": 0.9467, | |
| "eval_samples_per_second": 119.362, | |
| "eval_steps_per_second": 15.845, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3880597014925373, | |
| "grad_norm": 0.39158010482788086, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 2.1612, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.40298507462686567, | |
| "grad_norm": 0.42965012788772583, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 2.2331, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.417910447761194, | |
| "grad_norm": 0.4510224759578705, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 2.1721, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.43283582089552236, | |
| "grad_norm": 0.4704110622406006, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 2.0252, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.44776119402985076, | |
| "grad_norm": 0.5712336301803589, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 2.0158, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4626865671641791, | |
| "grad_norm": 0.5858246684074402, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 2.0812, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.47761194029850745, | |
| "grad_norm": 0.9474906325340271, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 2.0843, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4925373134328358, | |
| "grad_norm": 0.24608998000621796, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.6666, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5074626865671642, | |
| "grad_norm": 0.2545487582683563, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.8542, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5223880597014925, | |
| "grad_norm": 0.25772571563720703, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.8961, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5373134328358209, | |
| "grad_norm": 0.3282116949558258, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.9271, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5522388059701493, | |
| "grad_norm": 0.30054324865341187, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.99, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5671641791044776, | |
| "grad_norm": 0.33032283186912537, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.9075, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.582089552238806, | |
| "grad_norm": 0.3541136384010315, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 2.1065, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5970149253731343, | |
| "grad_norm": 0.36783766746520996, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 2.1716, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6119402985074627, | |
| "grad_norm": 0.3704308569431305, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 2.0668, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6268656716417911, | |
| "grad_norm": 0.41871926188468933, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 2.0886, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6417910447761194, | |
| "grad_norm": 0.4612567126750946, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 2.176, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6567164179104478, | |
| "grad_norm": 0.43885257840156555, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 2.0272, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6716417910447762, | |
| "grad_norm": 0.5096978545188904, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 2.1226, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6865671641791045, | |
| "grad_norm": 0.49920862913131714, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 1.8736, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7014925373134329, | |
| "grad_norm": 0.6098780632019043, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 1.9208, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7164179104477612, | |
| "grad_norm": 0.7482870817184448, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 1.972, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7313432835820896, | |
| "grad_norm": 0.2268557995557785, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 1.6986, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "grad_norm": 0.2336985319852829, | |
| "learning_rate": 0.0, | |
| "loss": 1.7152, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.746268656716418, | |
| "eval_loss": 1.9968057870864868, | |
| "eval_runtime": 0.9661, | |
| "eval_samples_per_second": 116.963, | |
| "eval_steps_per_second": 15.526, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 704570172899328.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |